Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 269  49  81 194  82 405 551 366 734 602 788 505 847 732  85  62 134 873 926 245
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1]  49 269 732  NA  82 551 734 788 194 245  62 366 405  NA 926 505  85 847  NA  81 873 134 602
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 2 5 4 5 4 1 2 3 4 2
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "c" "o" "k" "e" "d" "U" "W" "K" "G" "I"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 19
which( manyNumbersWithNA > 900 )
[1] 15
which( is.na( manyNumbersWithNA ) )
[1]  4 14 19

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 926
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 926
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 926

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "U" "W" "K" "G" "I"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "c" "o" "k" "e" "d"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  6  7  8 12
sum( manyNumbers %in% 300:600 )
[1] 4

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "small" "large" NA      "small" "large" "large" "large" "small" "small" "small" "small" "small" NA      "large" "large" "small" "large" NA      "small" "large"
[22] "small" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "small"   "large"   "UNKNOWN" "small"   "large"   "large"   "large"   "small"   "small"   "small"   "small"   "small"   "UNKNOWN" "large"   "large"   "small"  
[18] "large"   "UNKNOWN" "small"   "large"   "small"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0   0 732  NA   0 551 734 788   0   0   0   0   0  NA 926 505   0 847  NA   0 873   0 602

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 2 5 4 1 3
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  2  5  4  1  3
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE  TRUE FALSE  TRUE FALSE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 15
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 926
which.min( manyNumbersWithNA )
[1] 1
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 49
range( manyNumbersWithNA, na.rm = TRUE )
[1]  49 926

Sorting/ordering of vectors

manyNumbersWithNA
 [1]  49 269 732  NA  82 551 734 788 194 245  62 366 405  NA 926 505  85 847  NA  81 873 134 602
sort( manyNumbersWithNA )
 [1]  49  62  81  82  85 134 194 245 269 366 405 505 551 602 732 734 788 847 873 926
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  49  62  81  82  85 134 194 245 269 366 405 505 551 602 732 734 788 847 873 926  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 926 873 847 788 734 732 602 551 505 405 366 269 245 194 134  85  82  81  62  49  NA  NA  NA
manyNumbersWithNA[1:5]
[1]  49 269 732  NA  82
order( manyNumbersWithNA[1:5] )
[1] 1 5 2 3 4
rank( manyNumbersWithNA[1:5] )
[1] 1 3 4 5 2
sort( mixedLetters )
 [1] "c" "d" "e" "G" "I" "k" "K" "o" "U" "W"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  5.5  8.5  1.5  5.5  1.5 10.0  3.0  8.5  5.5  5.5
rank( manyDuplicates, ties.method = "min" )
 [1]  4  8  1  4  1 10  3  8  4  4
rank( manyDuplicates, ties.method = "random" )
 [1]  7  8  1  5  2 10  3  9  4  6

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000  0.75134619 -0.08287224  0.93421333 -0.09851515  1.25550389 -0.82291997  0.65503815 -0.18582365 -0.74296432
[15]  1.15346329
round( v, 0 )
 [1] -1  0  0  0  1  1  0  1  0  1 -1  1  0 -1  1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.8 -0.1  0.9 -0.1  1.3 -0.8  0.7 -0.2 -0.7  1.2
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.75 -0.08  0.93 -0.10  1.26 -0.82  0.66 -0.19 -0.74  1.15
floor( v )
 [1] -1 -1  0  0  1  0 -1  0 -1  1 -1  0 -1 -1  1
ceiling( v )
 [1] -1  0  0  1  1  1  0  1  0  2  0  1  0  0  2

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2023 Biomedical Data Sciences (BDS) | LUMC